Research hypothesis and level of significance - PDF.pptx

Research hypothesis definition, research hypothesis nature, research hypothesis functions, research hypothesis kinds, research hypothesis testing, Null hypothesis, level of significance, probability value (P value), type I and type II error, variables in research hypothesis, criteria for evaluation the research hypothesis.

1. Research Hypothesis   By Suad Zuhair B. Pharm, M. Pharm.  Clin .  Pharmacol .

2. A tentative solution of a problem which after testing either accepted or rejected. Research hypothesis Testing of research hypothesis by Suad Zuhair, B. Pharm, M. Pharm.

3. Meaning of hypothesis Hypo + thesis = Hypothesis ‘Hypo’ means tentative or subject to the verification (Greek root) ‘Thesis’ means statement about solution of a problem. A tentative statement about the solution of the Problem. A statement temporarily accepted as true in the light of what is known at the time about the phenomena. by Suad Zuhair, B. Pharm, M. Pharm.

4. DEFINITIONS OF HYPOTHESIS “It is a tentative supposition or provisional guess which seems to explain the situation under observation.” – James E. Greighton “ A hypothesis is a tentative generalization the validity of which remains to be tested. In its most elementary stage the hypothesis may be any hunch, guess, imaginative idea which becomes the basis for further investigation.” - Lungberg “A hypothesis states what we are looking for. A hypothesis looks forward. It is a proposition which can be put to a test to determine its validity. It may prove to be correct or incorrect.” - Goode and Han by Suad Zuhair, B. Pharm, M. Pharm.

5. Example The research problem: After the use of cinnamon some people complain from fainting. The research problem selection: the efficacy of cinnamon in hyperglycemia. The research statement: to determine the efficacy of cinnamon bark extract in lowering blood sugar in diabetogenic rat models. Literature review: We go to literature and found that in traditional medicine it is used to lower hyperglycemia. The hypothesis for this problem will be: “cinnamon has antidiabetic effect” If the literature said that the traditional use was for hypertension what is the hypothesis for this problem? by Suad Zuhair, B. Pharm, M. Pharm.

6. NATURE OF HYPOTHESIS It is conceptual in nature. It is a verbal statement. It has the empirical referent. It has a forward or future reference. It is the pivot of a scientific research. Derivable from known or available evidence. by Suad Zuhair, B. Pharm, M. Pharm.

7. FUNCTIONS OF HYPOTHESIS A temporary solution enables an investigator to start his research work [Guide] Offers a basis in establishing the specifics what to study for.[bridge between the problem and empirical evidence] May lead to formulate another hypothesis. Provides the investigator with definite statement which may be objectively tested and accepted or rejected. Leads for interpreting results and drawing conclusions that is related to original purpose. by Suad Zuhair, B. Pharm, M. Pharm.

8. KINDS OF HYPOTHESES Question form Hypotheses: represents the simplest level of empirical observation. Is there a significant interaction effect of drug dosage form and dosing interval on patient compliance? (b) Declarative Statement: an anticipated relationship or difference between variables. There is a significant interaction effect of drug dosage form and dosing interval on patient compliance. (c) Directional Hypothesis: connotes an expected direction in the relationship or difference between variables. Oral formulations with single daily dosage are easier to use whereas oral formulations with multiple dosage is complicated. (d) Non-Directional (Null) Hypothesis: stated in the null form which is an assertion that no relationship or no difference exists between or among the variables. There is no significant interaction effect of drug dosage form and dosing interval on patient compliance by Suad Zuhair, B. Pharm, M. Pharm.

9. Role of hypothesis Hypothesis is the basis of a research investigation. All research activities are oriented towards the verification of the hypotheses, and not to find out the solution of the problem or to seek an answer of a question. The form of the hypotheses to be tested can be very controversial. The null form is probably preferred by most experienced research personnel. by Suad Zuhair, B. Pharm, M. Pharm.

10. Null hypothesis (H0) [Null Hypothesis is a statistical hypothesis which is used in analyzing the data] It must be testable within the framework of probability theory. It assumes that the observed* difference or relationship (from collected data) is attributable by sampling error and true difference or relationship is zero. After the collected data is statistically tested (analyzed), the previous observed difference or relationship is either found to be significant or not. This is called “ Hypothesis testing ” And the null hypothesis is either accepted or rejected . If H0 is rejected , the alternative hypothesis (H1) is accepted . by Suad Zuhair, B. Pharm, M. Pharm.

11. Significance testing and significant level in null hypothesis Significance testing: is a test for the probability that the event could have occurred by chance. Significance (probability) level “P value”: the probability that the event could have occurred by chance. [The most acceptable P value is 0.05] If the level is quite low, that is, the probability of occurring by chance is quite small (less than or equal to 0.05, i.e. only 5% chance), we say the event is significant. [ by Suad Zuhair, B. Pharm, M. Pharm.

12. The more the unlikely data (occurred or observed rarely or only once) in our results, the more is the probability of chance. And the more the mean does not represent the data well. And the larger the standard deviation . The more the likely data (occurred or observed frequently with close values; i.e. data accumulation within narrow range) in our results, the least is the probability of chance. And the more the mean does represent the data too well. And the smaller the standard deviation . by Suad Zuhair, B. Pharm, M. Pharm.

13. Example If we want to test the cure rate of an anticancer drug Q with a dose P in 15 patients. The null hypothesis is: there is no significant cure rate for drug Q with the dose R. If the accepted P value is 0.05 and the calculated P value was found to be 0.15. Then the null hypothesis is accepted, and the observed cure rates is attributed to chance. by Suad Zuhair, B. Pharm, M. Pharm.

14. The result for null hypothesis testing involves two types of errors, either: Type I error (alpha error) : When null hypothesis (H0) is rejected while it should be accepted. It falsely shows that obtained difference exists and not due to chance or sampling errors. Type II error (beta error): When null hypothesis H0 is accepted while it should be rejected. It is falsely indicates that obtained difference is due to chance or sampling error. Reject H0 (or accept H1) False negative “Type I error” True negative “Correct” Accept H0 (or reject H1) False positive “Type II error ” True positive “Correct” by Suad Zuhair, B. Pharm, M. Pharm.

15. Note When fact finding alone is the primary aim of the study, it may not always be necessary to formulate an explicit hypothesis. by Suad Zuhair, B. Pharm, M. Pharm.

16. Variables in hypothesis The Independent Variable: It is the cause for change in other variables. [stimulus/input] [manipulated] The Dependent Variable: It is the variable that will change as a result of variations in the independent variable. [response/output] [measured] The Moderator Variable: a secondary independent variable selected for study to determine if it affects the relationship between the primary independent variable and the dependent variable. [manipulated] The control variable: those factors which are controlled by experimenter to cancel out or neutralize any effect they might otherwise have on the observed phenomena. [not measured] Intervening Variable: Is that factor which affects the observed phenomenon but cannot be seen and measured or manipulated. [Cannot be measured or manipulated] There are five types of variable: Example: Among students of the same age and intelligence, skill performance is directly related to the number of practice traits particularly among boys but less directly among girls. ( i ) Independent variable – number of practice trails. (ii) Dependent variable – skill performance. (iii) Moderator variable – sex. (iv) Control variable – age, intelligence. (v) Intervening variable – learning by Suad Zuhair, B. Pharm, M. Pharm.

17. Criteria for evaluation of hypothesis Plausibility of Explanation hypothesis that have relevant and logical possibility about the relationship of variables included in them. Testability of Explanation hypothesis variables should be defined operationally and the predicted relations among them can be tested empirically. Adequacy of Scope : a hypotheses that explain all the facts that are relevant to the phenomena being explained, establishes a generalization, or gives predictions about yet unobserved events and relationships (new hypothesis). Usefulness of False Hypotheses By eliminating the false hypotheses one by one the investigator keeps narrowing the field in which the answer must lie. Roots in Existing Theories A hypothesis that is compatible with well-attested theories is in a favorable position to advance knowledge. By supporting, qualifying, refuting or enlarging upon them. Suitability for Intended Purpose offers a satisfactory explanation of what it intends to explain. Simplicity of Explanation Levels of Explanation leads to fact, theory, or law by Suad Zuhair, B. Pharm, M. Pharm.

18. «حسبي الله ونعم الوكيل» by Suad Zuhair, B. Pharm, M. Pharm.